Sparsemax activation function

layer_sparsemax(object, axis = -1, ...)

Arguments

object	Model or layer object
axis	Integer, axis along which the sparsemax normalization is applied.
...	additional parameters to pass

Value

A tensor

Details

The output shape is the same as the input shape. https://arxiv.org/abs/1602.02068

Examples


if (FALSE) {
model = keras_model_sequential() %>%
  layer_conv_2d(filters = 10, kernel_size = c(3,3),input_shape = c(28,28,1),
                activation = activation_gelu) %>%
  layer_sparsemax()
}